数据和知识驱动的空战目标集群类型综合识别
收稿日期: 2022-04-11
修回日期: 2022-05-11
录用日期: 2022-06-20
网络出版日期: 2022-06-27
基金资助
国家自然科学基金(61873205)
Comprehensive recognization of aerial combat target cluster type driven by data and knowledge
Received date: 2022-04-11
Revised date: 2022-05-11
Accepted date: 2022-06-20
Online published: 2022-06-27
Supported by
National Natural Science Foundation of China(61873205)
目标集群类型识别是体系作战样式下态势认知的关键,然而现有集群识别算法主要依据专家知识人工进行判读,难以满足作战态势快速、准确理解的需求。提出数据和知识驱动下的推理机制,构建分层精细化推理的集群场景识别框架,预识别层检测目标运动过程中的集群的分群/合群,根据设计基于边界检测的密度峰值聚类确定群的划分情况,得到集群的初步识别结果;再识别层中综合分析集群执行任务、运动特性、电磁特性,对集群目标的多源特性进行多元知识约束下的推理网络构建,在此基础上利用现有数据进行推理网络参数学习,进而使推理获得更为准确的集群类型识别结果。该框架综合知识和数据的优势具有从粗到精的集群目标识别能力,利用多特征综合推理机制对目标集群精细化分析,实现集群类型的准确识别。在典型的集群作战活动场景下推理置信度和正确率两项指标均优于现有算法,验证了所提方法的有效性,提高空战目标集群类型识别的置信度和准确率。
张会霞 , 梁彦 , 马超雄 , 汪冕 , 乔殿峰 . 数据和知识驱动的空战目标集群类型综合识别[J]. 航空学报, 2023 , 44(8) : 327266 -327266 . DOI: 10.7527/S1000-6893.2022.27266
Identification of cluster types is the key to judging the cognition of combat situation. However, the existing cluster type identification algorithms are mainly based on expert knowledge for manual interpretation, imposing difficulty in satisfying the needs of rapid and accurate understanding of combat situation. To address this problem, we propose a reasoning mechanism driven by data and knowledge, constructing a cluster scene recognition framework for hierarchical refined reasoning. The pre-recognition layer detects the declustering/clustering of clusters during target movement, and determines the clustering based on the design of boundary detection-based density peaks clustering. Then, according to the division of the cluster, the preliminary identification results of the cluster are obtained. In the re-identification layer, the cluster execution tasks, motion characteristics, and electromagnetic characteristics are comprehensively analyzed and further utilized to construct an inference network under the constraint of multi-knowledge on the multi-source characteristics of the cluster target. Then, the existing data is used to learn the parameters of the inference network so that it can obtain more accurate cluster type identification results. The framework integrates knowledge and data to enable coarse to fine cluster target recognition, where the multi-feature comprehensive reasoning mechanism is used to comprehensively identify target clusters. This study realizes the refined identification of the cluster type, and the two indicators of inference confidence and accuracy are better than the existing algorithms in the typical cluster combat scenario, demonstrating the effectiveness of the proposed algorithm and improving the confidence and accuracy of aerial combat target cluster type identification.
1 | 祝学军, 赵长见, 梁卓, 等. OODA智能赋能技术发展思考[J]. 航空学报, 2021, 42(4): 524332. |
ZHU X J, ZHAO C J, LIANG Z, et al. Thoughts on technology development of OODA empowered with AI[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4): 524332 (in Chinese). | |
2 | 孙智孝, 杨晟琦, 朴海音, 等. 未来智能空战发展综述[J]. 航空学报, 2021, 42(8): 525799. |
SUN Z X, YANG S Q, PIAO H Y, et al. A survey of air combat artificial intelligence[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(8): 525799 (in Chinese). | |
3 | PURSER J L. Multi-domain operations and information warfare in the European theater[J]. Military Review, 2020, 100(6): 58-65. |
4 | 李保雪. 舰艇编队基本作战样式浅析[J]. 中国新通信, 2017, 19(17): 163-164. |
LI B X. Analysis on the basic combat style of warship formation[J]. China New Telecommunications, 2017, 19(17): 163-164 (in Chinese). | |
5 | XU D K, TIAN Y J. A comprehensive survey of clustering algorithms[J]. Annals of Data Science, 2015, 2(2): 165-193. |
6 | XIE J Y, JIANG S, XIE W X, et al. An efficient global K-means clustering algorithm[J]. Journal of Computers, 2011, 6(2): 271-279. |
7 | LIANG Z. Delta-density based clustering with a divide-and-conquer strategy: 3DC clustering[J]. Pattern Recognition Letters, 2016, 73: 52-59. |
8 | RODRIGUEZ A, LAIO A. Clustering by fast search and find of density peaks[J]. Science, 2014, 344(6191): 1492-1496. |
9 | JIANG J H, ZHOU W, WANG L M, et al. HaloDPC: An improved recognition method on halo node for density peak clustering algorithm[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2019, 33(8): 1950012. |
10 | JIANG J H. A novel density peaks clustering algorithm based on K[J]. Physica A: Statistical Mechanics and Its Applications, 2019, 523: 702-713. |
11 | CHEN X J. Research on sea battlefield data fusion method based on D-S evidential theory and event net[J]. DEStech Transactions on Computer Science and Engineering, 2018: 625-631. |
12 | 孙宇翔, 黄孝鹏, 周献中, 等. 基于知识的海战场态势评估辅助决策系统构建[J]. 指挥信息系统与技术, 2020, 11(4): 15-20. |
SUN Y X, HUANG X P, ZHOU X Z, et al. Construction of knowledge-based situation assessment and assistant decision-making system for sea battlefield[J]. Command Information System and Technology, 2020, 11(4): 15-20 (in Chinese). | |
13 | AZAREWICZ J, FALA G, HEITHECKER C. Template-based multi-agent plan recognition for tactical situation assessment[C]∥ The Fifth Conference on Artificial Intelligence Applications. Piscataway: IEEE Press, 1989: 247-254. |
14 | 柴慧敏, 王宝树. 基于分层贝叶斯网络的计划识别方法[J]. 系统工程与电子技术, 2008, 30(5): 964-967. |
CHAI H M, WANG B S. Method for plan recognition based on hierarchical Bayesian networks[J]. Systems Engineering and Electronics, 2008, 30(5): 964-967 (in Chinese). | |
15 | XU L X, QIAO D F, LIANG Y, et al. A novel DBN-based intention inference algorithm for warship air combat[C]∥ 2020 IEEE 9th Joint International Information Technology and Artificial Intelligence Conference. Piscataway: IEEE Press, 2020: 916-921. |
16 | MEI W, LIU L, DONG J. The integrated sigma-max system and its application in target recognition[J]. Information Sciences, 2021, 555: 198-214. |
17 | 刘雷, 刘大卫, 王晓光, 等. 无人机集群与反无人机集群发展现状及展望[J]. 航空学报, 2022, 43(S1): 726908. |
LIU L, LIU D W, WANG X G, et al. Development status and outlook of UAV clusters and anti-UAV clusters[J]. Acta Aeronautica et Astronautica Sinica, 2022, 43(S1): 726908 (in Chinese). | |
18 | 陈士涛, 李大喜, 孙鹏, 等. 美军智能无人机集群作战样式及影响分析[J]. 中国电子科学研究院学报, 2021, 16(11): 1113-1118. |
CHEN S T, LI D X, SUN P, et al. Analysis on the development and influence of intelligent unmanned aerial vehicle cluster in US army[J]. Journal of China Academy of Electronics and Information Technology, 2021, 16(11): 1113-1118 (in Chinese). | |
19 | LIU W F. Structure modeling and estimation of multiple resolvable group targets via graph theory and multi-Bernoulli filter[J]. Automatica, 2018, 89: 274-289. |
20 | LIU S, LIANG Y, XU L F, et al. EM-based extended object tracking without a priori extension evolution model[J]. Signal Processing, 2021, 188: 108181. |
21 | 乔殿峰, 梁彦, 马超雄, 等. 多域作战下的群目标意图识别与预测[J]. 系统工程与电子技术, 2022: 44(11): 3403-3412. |
QIAO D F, LIANG Y, MA C X, et al. Recognition and prediction of group target intention in multi-domain operations[J/OL]. Systems Engineering and Electronics, 2022: 44(11): 3403-3412 (in Chinese). | |
22 | 胡利平, 梁晓龙, 何吕龙, 等. 基于情景分析的航空集群决策规则库构建方法[J]. 航空学报, 2020, 41(S1): 723737. |
HU L P, LIANG X L, HE L L, et al. Construction method of aviation swarm decision rule base based on scenario analysis[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41(S1): 723737 (in Chinese). | |
23 | 王书敏. 体系作战运筹分析[M]. 北京: 军事科学出版社, 2018: 639-399. |
WANG S M. Operations analysis on system-of-systems combat[M]. Beijing: Military Science Publishing House, 2018: 639-399 (in Chinese). | |
24 | HE J, WANG Y D, LIANG Y, et al. Learning-based airborne sensor task assignment in unknown dynamic environments[J]. Engineering Applications of Artificial Intelligence, 2022, 111: 104747. |
25 | 王莹. 用频装备面临的电磁环境量化方法研究[D]. 哈尔滨: 哈尔滨工程大学, 2013: 15-18. |
WANG Y. Study on quantitative methods of electromagnetic environment around electronic equipments[D]. Harbin: Harbin Engineering University, 2013: 15-18 (in Chinese). | |
26 | Wu Y, Du Y J, Zhang Y K. Evaluation of region electromagnetic environment complexity based on propagation model[J]. Journal of Computational Information Systems, 2014, 14(10): 5987-5994. |
27 | MEI W, SHAN G, WANG Y F. A second-order uncertainty model for target classification using kinematic data[J]. Information Fusion, 2011, 12(2): 105-110. |
28 | ZHANG D Z, LEE K, LEE I. Hierarchical trajectory clustering for spatio-temporal periodic pattern mining[J]. Expert Systems With Applications, 2018, 92: 1-11. |
29 | 万昌豪, 刘志国, 唐圣金, 等. 基于不完美先验信息的随机系数回归模型剩余寿命预测方法[J]. 北京航空航天大学学报, 2021, 47(12): 2542-2551. |
WAN C H, LIU Z G, TANG S J, et al. Remaining useful life prediction method based on random coefficient regression model with imperfect prior information[J]. Journal of Beijing University of Aeronautics and Astronautics, 2021, 47(12): 2542-2551 (in Chinese). | |
30 | 叶思懋. 融合先验的贝叶斯网络结构学习及其在智能决策中的应用[D]. 西安: 西北工业大学, 2018: 10-25. |
YE S M. Learning Bayesian network structure with priors and the application to intelligent decision[D]. Xi’an: Northwestern Polytechnical University, 2018: 10-25 (in Chinese). | |
31 | FORTIN B, HACHOUR S, DELMOTTE F. Multi-target PHD tracking and classification using imprecise likelihoods[J]. International Journal of Approximate Reasoning, 2017, 90: 17-36. |
/
〈 |
|
〉 |